nbeerbower/llama-3-stella-truthy-dpo-8B
LoRA-style vs nbeerbower/llama-3-stella-8B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128
3 derivatives checked
- mradermacher/llama-3-stella-truthy-dpo-8B-GGUF: Same weights, converted
- featherless-ai-quants/nbeerbower-llama-3-stella-truthy-dpo-8B-GGUF: Quantization
- flammenai/Mahou-1.0-llama3-8B: LoRA-style